COVID-19 Announcement

We are closely monitoring the situation with the ongoing COVID-19 pandemic. Authors of accepted papers will not be obliged to travel, they will have the opportunity to present the work remotely.


The International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms (HeteroPar'2021) will be held, in its nineteenth edition in Lisbon, Portugal. For the 12th time, this workshop is organized in conjunction with the EURO-PAR annual series of international conferences dedicated to the promotion and advancement of all aspects of parallel computing.

Workshop scope

Heterogeneity is emerging as one of the most profound and challenging characteristics of today's parallel environments. From the macro level, where networks of distributed computers, composed of diverse node architectures, are interconnected with potentially heterogeneous networks, to the micro level, where deeper memory hierarchies and various accelerator architectures are increasingly common, the impact of heterogeneity on all computing tasks is increasing rapidly. Traditional parallel algorithms, programming environments and tools, designed for legacy homogeneous multiprocessors, will at best achieve a small fraction of the efficiency and the potential performance that we should expect from parallel computing in tomorrow's highly diversified and mixed environments. New ideas, innovative algorithms, and specialized programming environments and tools are needed to efficiently use these new and multifarious parallel architectures. The workshop is intended to be a forum for researchers working on algorithms, programming languages, tools, and theoretical models aimed at efficiently solving problems on heterogeneous platforms.

Topics to be covered include but are not limited to:

  • Heterogeneous parallel programming paradigms and models

  • Languages, libraries, and interfaces for different heterogeneous parallel programming models

  • Performance models and their integration into the design of efficient parallel algorithms for heterogeneous platforms

  • Parallel algorithms for heterogeneous and/or hierarchical systems, including manycores and hardware accelerators (FPGAs, GPUs, etc.)

  • Parallel algorithms for efficient problem solving on heterogeneous platforms (numerical linear algebra, nonlinear systems, fast transforms, computational biology, data mining, multimedia, etc.)

  • Software engineering for heterogeneous parallel systems

  • Applications on heterogeneous platforms

  • Algorithms, models and tools for energy optimization on heterogeneous platforms

  • Bi-objective optimization of applications on heterogeneous platforms for performance and energy

  • Integration of parallel and distributed computing on heterogeneous platforms

  • Experience of porting parallel software from supercomputers to heterogeneous platforms

  • Fault tolerance of parallel computations on heterogeneous platforms

  • Algorithms, models and tools for grid, desktop grid, cloud, and green computing

Authors are encouraged to submit original, unpublished research or overviews on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms, namely addressing the topics referred above.


NEW deadline extension: new submission deadline is June 13th

Journal Special Issue Authors of selected papers accepted for presentation at HeteroPar'2021 will be invited to submit a revised and extended version of their work to a special issue of Wiley's Concurrency and Computation Practice and Experience journal.

Workshop Program

Session 6A: DL and heterogeneous computing
9:00 - 9:50 Keynote: Jose Flich, Towards High Level Synthesis Support in the European Deep Learning Library
9:50 - 10:15 Daxiang Dong, Ji Liu, Xi Wang, Weibao Gong, An Qin, Xingjian Li, Dianhai Yu, Patrick Valduriez and Dejing Dou, "Elastic Deep Learning using Knowledge Distillation with Heterogeneous Computing Resources"
10:30 - 10:50 Coffee break
Session 7A: Algorithm and kernels in heterogeneous computing
10:50 - 11:15 Yu-Hsiang Tsai, Terry Cojean and Hartwig Anzt, "Porting Sparse Linear Algebra to Intel GPUs"
11:15 - 11:40 Pablo Vizcaino, Filippo Mantovani and Jesus Labarta, "Accelerating FFT using NEC SX-Aurora Vector Engine"
11:40 - 12:05 Hamidreza Khaleghzadeh, Ravi Reddy Manumachu and Alexey Lastovetsky, "A Novel Bi-Objective Optimization Algorithm on Heterogeneous HPC Platforms for Applications with Continuous Performance and Linear Energy Profiles"
12:05 - 12:30 Renzo Marini, Ernesto Dufrechou and Pablo Ezzatti, "Towards an efficient sparse storage format for the SpMM kernel in GPUs"
12:30 - 13:30 Lunch Break
Session 8A: Runtime and data management models
13:30 - 13:55 Pawel Bratek, Lukasz Szustak, Roman Wyrzykowski, Tomasz Olas and Tomasz Chmiel, "Heterogeneous Voltage Frequency Scaling of Data-Parallel Applications for Energy Saving on Homogeneous Multicore Platforms"
13:55 - 14:20 Erwan Lenormand, Thierry Goubier, Loïc Cudennec and Henri-Pierre Charle, "Data management model to program irregular compute kernels on FPGA: application to heterogeneous distributed system"
14:20 - 14:45 Jared O'Neal, Mohamed Wahib, Anshu Dubey, Klaus Weide, Tom Klosterman and Johann Rudi, "Domain-Specific Runtime to Orchestrate Computation on Heterogeneous Platforms"
14:45 - 15:15 Coffee break
Session 9A-1: Heterogeneous computing with OpenCL
15:15 - 15:40 John Stratton, Jyothi Krishna V S, Jeevitha Palanisamy and Karthikadevi Chinnaraju, "Kernel Fusion in OpenCL"
15:40 - 16:05 Raúl Nozal, Christoph Niethammer, José Gracia a Jose Luis Bosque, "Feasibility study of Molecular Dynamics kernels exploitation using EngineCL"
Session 9A-2: Cloud computing
16:05 - 16:30 Pawel Koperek, Wlodzimierz Funika and Jacek Kitowski, "Continuous Self-Adaptation of Control Policies in Automatic Cloud Management"
16:30 - 16:55 Jakub Gasior and Franciszek Seredynski, "An Automata-based Approach to Profit Optimization of Cloud Brokers in IaaS Environment"
16:55 - 17:00 Workshop conclusion

Keynote Speaker

Keynote speaker: José Flich

Title: Towards High Level Synthesis Support in the European Deep Learning Library

Abstract: The support of inference processes on FPGA devices is common today. Indeed, FPGAs are a cost-effective and energy-efficient alternative to other architectures such as CPUs or GPUs. With the aim of providing an European toolkit for Deep Learning, the H2020 DeepHealth project is developing the EDDL library (European Distributed Deep-learning Library). This library targets distributed training on HPC infrastructures with CPUs and GPUs. Support is also being provisioned for inference processes on FPGA devices. In this talk, we will review the effort developed within the DeepHealth project (and other associated projects) for the support of efficient inference processes by EDDL on FPGA devices. High Level Synthesis (HLS) is used for development of accelerator units mastered by the EDDL API. In the talk we will review the design alternatives and the choices we took, comparing our solution with more standard accelerator units available today.

Short bio: José Flich is Professor at Universitat Politècnica de València where for the last 25 years he teaches subjects related to Computer Architecture and Interconnection Networks. José Flich has published more than 100 and 50 peer-reviewed conference and journal papers, respectively. His research has been focused mainly on interconnection networks for HPC systems, Networks on Chip designs, and recently on the applicability of FPGA devices for emulation of NoCs and multicore systems and on the use of FPGAs as computing platform. He has coordinated several European Projects (FP7 NaNoC project and H2020 MANGO project) and participated as IP in others (RECIPE, DeepHealth, eFlows4HPC). In the MANGO project a 192 FPGA cluster was built for the exploration of HPC architectures.

Paper submission

Authors are invited to submit papers electronically, through EasyChair
The papers should be submitted in PDF, following the Springer LNCS format .
Paper length must not exceed 12 pages (including references).

Paper submission deadline: June 13, 2021 (new extra extended date)
Authors notification: June 30, 2021

Important dates

Paper submission deadline: June 13, 2021 (extra extended date)
Authors notification: June 30, 2021

Information for authors

Accepted papers that are presented at the workshop, will be published in a revised form in a special Euro-Par Workshop Volume in the Lecture Notes in Computer Science (LNCS) series after the Euro-Par conference.

Contact Information

Rosa M Badia

Group Manager
Workflows and Distributed Computing
Barcelona Supercomputing Center